Search Results for author: Yinsong Xu

Found 3 papers, 1 papers with code

EviPrompt: A Training-Free Evidential Prompt Generation Method for Segment Anything Model in Medical Images

no code implementations10 Nov 2023 Yinsong Xu, Jiaqi Tang, Aidong Men, Qingchao Chen

Then, we incorporate the human prior into the prompts, which is vital for alleviating the domain gap between natural and medical images and enhancing the applicability and usefulness of SAM in medical scenarios.

Image Segmentation Medical Image Segmentation +1

Incorporating Pre-training Data Matters in Unsupervised Domain Adaptation

no code implementations6 Aug 2023 Yinsong Xu, Aidong Men, Yang Liu, Qingchao Chen

To answer the first question, we empirically observed an interesting Spontaneous Pulling (SP) Effect in fine-tuning where the discrepancies between any two of the three domains (ImageNet, Source, Target) decrease but at the cost of the impaired semantic structure of the pre-train domain.

Unsupervised Domain Adaptation

Delving into the Continuous Domain Adaptation

1 code implementation28 Aug 2022 Yinsong Xu, Zhuqing Jiang, Aidong Men, Yang Liu, Qingchao Chen

Existing domain adaptation methods assume that domain discrepancies are caused by a few discrete attributes and variations, e. g., art, real, painting, quickdraw, etc.

Attribute Domain Adaptation

Cannot find the paper you are looking for? You can Submit a new open access paper.